Interview setup
The setup is what turns generic AI output into answers that sound like you and reference work you actually did. It is worth the two minutes.
The interview setup form showing role selection, job description attachment, support type checkboxes, and the per-surface model picker.
public/docs/setup/setup-form.pngWhat to fill in
Role
The position you are interviewing for. This shapes vocabulary and the kind of examples the assistant reaches for. Be specific — "Senior Backend Engineer" produces better output than "Engineer".
Job description
Paste the posting. The assistant mirrors the language the company uses, which matters more than people expect: interviewers tend to score answers higher when they hear their own framing reflected back.
Resume and personal profile
Optional attachments, and the single highest-leverage thing you can add. With your resume attached, behavioral answers cite projects you actually shipped instead of inventing plausible ones.
Support types
Choose which surfaces this session needs — Chat, Coding, System design, or any combination. Only the ones you pick are prepared, so leaving out surfaces you will not use keeps the workspace uncluttered.
Programming language
Required when Coding is selected. Solutions come back idiomatic to the language you pick rather than translated out of Python.
C · C# · C++ · Dart · Elixir · Go · Java · JavaScript · Kotlin · PHP · Python · R · Ruby · Rust · Scala · SQL · Swift · TypeScript
Models
Assign a model per surface. See Choosing models for a recommended pairing.
Saving and reusing setups
Save a setup once and replay it. For a company loop where you have four rounds over two weeks, one saved setup covers all of them — and your interview history keeps every session separate so you can look back at what was asked.
The saved setups list in the left rail, showing several stored interview configurations with role and company labels.
public/docs/setup/saved-setups.png